Supercharge Your Innovation With Domain-Expert AI Agents!

Weighted recursive denoising deep neural network and method for multilayer convolution sparse coding

A convolutional sparse coding and deep neural network technology, applied in the field of image processing, can solve the problems of gradient disappearance, difficulty in recursive network, difficulty in learning distance pixels, etc., to avoid errors and avoid too few recursion times.

Pending Publication Date: 2021-09-03
SOUTHWEST UNIVERSITY
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the training of the recursive network is difficult. As the number of recursions increases, the depth of the network will gradually deepen. When the image feature information acquired at the shallow layer is transmitted to the deep layer of the network through a single recursive structure, it is easy to cause the problem of incomplete information utilization.
At the same time, learning between distant pixels will become difficult, and it may also face potential gradient disappearance and gradient explosion problems

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Weighted recursive denoising deep neural network and method for multilayer convolution sparse coding
  • Weighted recursive denoising deep neural network and method for multilayer convolution sparse coding
  • Weighted recursive denoising deep neural network and method for multilayer convolution sparse coding

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The description and claims do not use the difference in name as a way to distinguish components, but use the difference in function of the components as a criterion for distinguishing. As mentioned throughout the specification and claims, "including" is an open-ended term and should be interpreted as "including but not limited to". "Approximately" means that within an acceptable error range, those skilled in the art can solve the technical problem within a certain error range, and basically achieve the technical effect.

[0040] Orientation terms such as up and down, left and right in this description and the claims are combined with the accompanying drawings for the convenience of further description, making the application more convenient to understand, and do not limit the application. Relatively speaking.

[0041] The present invention will be further described in detail below with reference to the accompanying drawings.

[0042] Multilayer Convolutional Sparse Co...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides an end-to-end weighted recursive denoising convolutional neural network WRDnCN-LISTA + based on a multi-layer convolutional sparse coding (MLCSC) model, and the model is based on an expanded multi-layer learning iterative soft threshold algorithm (ML-LISTA), and introduces a recursive weighted supervision mechanism to realize natural image denoising. The expanded ML-LISTA algorithm can be in one-to-one correspondence with the convolutional neural network, and the weighted supervision mechanism can also improve the degradation problem brought by a simple recursive structure in the deep network. The introduced learnable weight uses output results of all intermediate recursions, so that the influence of different recursion times on the network performance is weakened, and the denoising performance is also enhanced. The specific parameter sharing property of the recursive network enables the parameter cost consumed for constructing a deep convolutional neural network to be reduced, and ensures that all parameters in the model can be adaptively updated by using back propagation through minimizing a loss function.

Description

technical field [0001] The invention relates to the technical field of image processing, more specifically, it relates to a weighted recursive denoising deep neural network and method of multi-layer convolution sparse coding. Background technique [0002] Image denoising is a crucial image processing problem in the field of computer vision. It is regarded as a preprocessing step for advanced vision problems and is widely used in practical applications such as medical image analysis, remote sensing imaging, and digital photography. Among them, the removal of additive Gaussian white noise (AGWN) from synthetic images has attracted a lot of research. This denoising task assumes that observed images contaminated by noise Y=X+V, where X is a potential clean image and V represents a known standard Additive white Gaussian noise with variance σ, through a denoising algorithm to obtain a potentially clean image from the polluted observation image Y. [0003] Existing image denoising...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06T5/00G06N3/04G06N3/08
CPCG06N3/08G06T2207/20081G06T2207/20084G06N3/045G06T5/70
Inventor 王建军文泽珈周敏龚英凡吴松
Owner SOUTHWEST UNIVERSITY
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More